Population: a set which includes all and asked them if they own pets. He found measurements of interest to the researcher that 90 of them did own a pet. He concluded (The collection of all responses, that 90% of all adults own pets. measurements, or counts that are of interest) Is this a valid conclusion? - NOT VALID because his samples Sample: A subset of the population are 100 adults who visited the zoo. People who visit the Zoo are usually Why sampling? fond of pets. This is an example of Impossible to study the whole population. biased sampling, and the 100 - Manageability of data samples are called biased sample. - Economic Reasons - Time and effort Kathy wants to know how many students in her city use the internet for learning Types of Sampling: purposes. She used an email poll. Based on ● Probability sampling- Each member the replies to her poll, she found that 83% of of the population is given equal those surveyed used the internet. chance or opportunity of being included in the sample. Kathy’s sample is BIASED as she surveyed ● Non-probability sampling- Each only those students who use the internet. member of the population does not have an equal chance or opportunity Non-Probability Sampling of being included in the sample. Convenience Sampling- The researcher Probability v/s Non-Probability uses subjects that are readily available or ● Probability sampling includes only people who are easy to reach. 1. You have a complete sampling Example: Using student volunteers as frame subjects for the research. 2. You can select a random sample from your population Purposive sampling- The researcher looks 3. You can generalize your results from for predefined groups that will serve as a random sample samples 4. Can be more expensive and example: The researcher wants to know time-consuming what it takes to graduate summa cum laude in college, the only people who can give the ● Non-Probability Sampling researcher first hand advise are the 1. Used when there isn’t an exhaustive individuals who graduated summa cum population list available. laude. 2. Not random 3. Can be effective when trying to Probability Sampling generate ideas and getting feedback ● Simple Random Sampling 4. More convenient and less costly ● Stratified Sampling ● Cluster Sampling Systematic sampling ● Systematic Sampling - It selects every kth member of the ● Multi-Stage Sampling population with the starting point determined at random Simple Random Sampling (SRS) - All members of the population have Sample Size (n) a chance of being included in the - Most statisticians agree that the sample. minimum sample size to get any kind of meaningful result is 100. If Example of SRS: your population is less than 100 then A credit card company wants to know the you really need to survey all of them. percentage of credit card holders who are satisfied with their new billing system. An A good maximum sample size is usually alphabetical listing of credit card holders is 10% as long as it does not exceed 1000 available. One thousand random numbers from a calculator will be generated. These For example: In a population of 5000, 10% random numbers will be used in getting the would be 500. In a population of 200,000, 1000 card holders from the alphabetical list. 10% would be 20,000. This exceeds 1000, so in this case, the maximum would be Stratified Sampling 1000. - This technique is use when the population can be subdivided into n=??? several smaller groups (or strata) IN RESEARCH: THE MORE SAMPLES WE and then SRS is applied to get GET THE BETTER! samples from each stratum The opinion of 1,000 people is always better Example of Stratified Sampling: than the opinion of 100 people! Students are grouped according to year level (i.e., grade 7, grade 8, grade 9 and Determining Sample Size grade 10.) One hundred representatives 1. Using A Census for Small from each group will be chosen for the study Population (n<100) on the student’s grades in science and 2. Using Sample Size which is 10% of mathematics. N 3. Using Published Tables Cluster Sampling 4. Using Formulas to Determine - This technique employs the use of Sample Size: Slovin’s Formula\ cluster (groups) instead of individuals that are randomly chosen If N is known: Slovin’s Formula: Example: All children in five chosen districts of Metro Manila will form a sample for the study of the occurrence of dengue fever in Metro Manila. n is the sample size N is the population size e is the margin of error
- To use the formula, first figure out
what you want your error of tolerance to be. - For example, you may be happy with a confidence level of 95 percent (giving a margin error of 0.05), or you may require a tighter accuracy of a 98 percent confidence level (a margin of error of 0.02). Plug your population size and required margin of error into the formula. The result will be the number of samples you need to take.